Name: lakebase-setup
Rating: 83.2 (1 reviews)
Author: databricks

lakebase-setup

Configure Lakebase for agent memory storage. Use when: (1) Adding memory capabilities to the agent, (2) 'Failed to connect to Lakebase' errors, (3) Permission errors on checkpoint/store tables, (4) User says 'lakebase', 'memory setup', or 'add memory'.

3.40x

Quality

—

Does it follow best practices?

Impact

92%

3.40x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete commands, complete configs, and a strong troubleshooting table, and the overall 7-step workflow is easy to follow. It loses points for redundancy (duplicated YAML, overlapping Overview/Use Cases, a broken Step 5 header), a missing final verification checkpoint, and heavy inlining of content that would be better split into reference files.

Suggestions

Remove the duplicated "Complete Examples" YAML (or replace it with a pointer to a single canonical example) and consolidate the overlapping Overview and Use Cases sections to tighten token use and fix the stray "## Step 5: Initialize Tables" header.

Add an explicit verification checkpoint after Step 7 (e.g., a command or check confirming the app started and tables were created) to close the destructive/permission workflow's feedback loop.

Move the LakebaseClient API reference and full YAML examples into files under references/ and link to them one level deep, so SKILL.md acts as an overview rather than a monolith.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but contains real redundancy: the Overview and Use Cases sections overlap, the ~110-line "Complete Examples" block repeats the YAML already shown in Step 3, and there is a stray "## Step 5: Initialize Tables" header with no body. Not level 3 because not every token earns its place; not level 1 because it does not pad with concepts Claude already knows.	2 / 3
Actionability	Guidance is concrete and copy-paste ready: executable commands (uv sync, databricks api get, databricks bundle deploy, the grant script with a template-to-type table), complete YAML and .env blocks, and a troubleshooting table mapping specific error strings to fixes.	3 / 3
Workflow Clarity	A clear 7-step sequence with an ASCII diagram, a CRITICAL permission warning, and troubleshooting feedback loops is present, but the broken duplicate Step 5 header and the absence of an explicit post-deploy/post-run verification checkpoint prevent a top score; the guideline caps destructive/permission workflows lacking verification at 2.	2 / 3
Progressive Disclosure	Section-level organization is decent, but substantial reference material (the LakebaseClient API reference, full duplicate YAML examples, large troubleshooting table) is inlined rather than split into separate files, and the few file references point outside this skill's own absent bundle (no references/ scripts/ or assets/ directories exist) instead of to well-signaled local reference files.	2 / 3
	Total	9 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is well-formed: it answers both what and when with explicit, natural trigger terms anchored on a distinctive product name. Its only weakness is that the capability statement is a single action rather than a comprehensive list of concrete actions.

Suggestions

Expand the capability clause beyond a single verb to list the concrete actions the skill performs (e.g., add the memory dependency, configure databricks.yml resources, grant service-principal Postgres permissions).

Disambiguate the "add memory" trigger from the sibling agent-memory skill to reduce overlap (e.g., scope it to "add Lakebase-backed memory").

Dimension	Reasoning	Score
Specificity	"Configure Lakebase for agent memory storage" names a concrete domain and a single primary action, but does not enumerate multiple distinct capabilities; the listed (1)-(4) items are trigger conditions rather than actions, so it stops short of the level-3 multi-action anchor.	2 / 3
Completeness	It states what the skill does ("Configure Lakebase for agent memory storage") and provides an explicit "Use when:" clause with four numbered triggers, satisfying both the what and the when.	3 / 3
Trigger Term Quality	Natural user-facing terms ("lakebase", "memory setup", "add memory") are present alongside realistic pasted error strings ("Failed to connect to Lakebase", "Permission errors on checkpoint/store tables"), giving good coverage of phrases users would actually say.	3 / 3
Distinctiveness Conflict Risk	The distinctive product name "lakebase" plus highly specific error-string triggers create a clear niche unlikely to fire for unrelated skills, despite minor overlap risk between "add memory" and a sibling agent-memory skill.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	15 / 16 Passed

Repository: databricks/app-templates
Commit: 2a4c792

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.